ABSTRACT
Lung cancer has become the most common malignant tumor in recent years. Tumor segmentation from medical images is substantial for the benign and malignant classification of tumors and the choice of subsequent therapy plans. Current diagnostic methods of standard lung images in clinic mainly depend on computed tomography (CT). Magnetic Resonance Imaging (MRI) has advantages of no radiation to human body and higher sensitivity to soft tissue lesions compared with CT. Multi-modality imaging is the attribute of MRI, which can give more information for tumor delineation. In this paper, we proposed a novel approach for the segmentation of lung tumors from multi-modal MR images which combines fully convolutional network (FCN) based semantic network (U-Net) and hyper-densely connected CNN model (Hyper-DenseNet) for multi-modality fusion. Our proposed method has two aspects of architecture: multi-modality feature fusion architecture and encoder-decoder based semantic segmentation architecture. The combination of these two architectures overcomes the deficiency of single modality U-Net and Hyper-DenseNet. The effectiveness of our proposed method has been demonstrated by comparative experiments on 564 scan slices of 89 lung cancer patients. Our method yields better experiment results by Dice Similarity Coefficient (DSC) to evaluation than single-modal U-Net and Hyper-DenseNet without encoder-decoder. The more encouraging result, especially, is that the segmentation results of the tumors adjacent to normal tissues and organs or the inflammatory tissues has a more remarkable improvement.
- F. B. Ahmedin Jemal, Melissa M. Center, Jacques Ferlay, Elizabeth Ward and David Forman, "Global cancer satatistics", CA: A Cancer Journal for Clinicians, 2011, vol. 61, pp. 69--90.Google ScholarCross Ref
- Cui H, Wang X, Feng D. "Automated localization and segmentation of lung tumor from PET-CT thorax volumes based on image feature analysis". Conf Proc IEEE Eng Med Biol Soc, 2012, 2012(4):5384--5387.Google Scholar
- J. S. Cooper, S. K. Mukherji, A. Y. Toledano, C. Beldon, I. M.Schmalfuss, R. Amdur, S. Sailer, L. A. Loevner, P. Kousouboris, K. K. Ang, J. Cormack, and J. Sicks, "An evaluation of the variability of tumor-shape definition derived by experienced observers from CT images of supraglottic carcinomas (ACRIN protocol 6658)," International Journal of Radiation Oncology Biology Physics, 2007, vol. 67, pp. 972--975.Google ScholarCross Ref
- H. Yu, C. Caldwell, K. Mah, and D. Mozeg, "Coregistered FDG PET/CT-Based Textural Characterization of Head and Neck Cancer for Radiation Treatment Planning," IEEE Transactions on Medical Imaging, 2009, vol. 28, pp. 374--383.Google ScholarCross Ref
- Schroeder T, Ruehm SG, Debatin JF, "Detection of pulmonary nodules using a 2D HASTE MR sequence: comparison with MDCT". AJR Am J Roentgenol. 2005, 185(4):979--84.Google ScholarCross Ref
- Long J, Shelhamer E, Darrell T. "Fully Convolutional Networks for Semantic Segmentation", IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 39(4), pp:640--651.Google ScholarDigital Library
- Olaf Ronneberger, Philipp Fischer, Thomas Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation", MICCAI, 2015, pp: 234--241Google ScholarCross Ref
- Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla, "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, vol.39, pp: 2481--2495Google ScholarCross Ref
- Noh H, Hong S, Han B. "Learning deconvolution network for semantic segmentation[C]", Proceedings of the IEEE international conference on computer vision. 2015: 1520--1528.Google Scholar
- K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. CVPR, 2016, pp. 770--778.Google Scholar
- G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, "Densely connected convolutional networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2017, pp. 4700--4708.Google Scholar
- Dolz J, Ayed I B, Jing Y, et al. "HyperDense-Net: A hyper-densely connected CNN for multi-modal image semantic segmentation[J]". IEEE Transactions on Medical Imaging, 2018, PP(99):1--1.Google Scholar
- Bilic P, Christ P F, Vorontsov E, et al. "The liver tumor segmentation benchmark (lits)[J]". arXiv preprint arXiv:1901.04056, 2019.Google Scholar
- K. He, X. Zhang, S. Ren, and J. Sun, "Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification," in Proc. IEEE ICCV, 2015, pp. 1026--1034.Google Scholar
- D. Nie, L. Wang, Y. Gao, and D. Sken, "Fully convolutional networks for multi-modality isointense infant brain image segmentation," in Proc. 13th Int. Symp. Biomed. Imag. (ISBI), 2016, pp. 1342--1345.Google Scholar
- F. Milletari, N. Navab, and S.-A. Ahmadi, "V-net: Fully convolutional neural networks for volumetric medical image segmentation," in Proc. 4th Int. Conf. 3D Vis. (3DV), 2016, pp. 565--5.Google Scholar
Index Terms
- A Novel Network Based on Densely Connected Fully Convolutional Networks for Segmentation of Lung Tumors on Multi-Modal MR Images
Recommendations
Lung tumor segmentation in PET images using graph cuts
The aim of segmentation of tumor regions in positron emission tomography (PET) is to provide more accurate measurements of tumor size and extension into adjacent structures, than is possible with visual assessment alone and hence improve patient ...
AMRSegNet: adaptive modality recalibration network for lung tumor segmentation on multi-modal MR images
AbstractSegmentation of lung tumor on magnetic resonance (MR) images is challenging. In this study, we propose an adaptive modality recalibration segmentation network (AMRSegNet) for lung tumor segmentation on T2-weighted (T2W) and diffusion-weighted ...
PET-CT image Co-segmentation of lung tumor using joint level set model
AbstractAccurate lung tumor segmentation plays an important role in radiotherapy and targeted therapy. Positron emission tomography (PET) and computed tomography (CT) scanner imaging provide complementary evidence for lung tumor segmentation. In specific,...
Comments